INDEX

Explanations

terms related to research institutions, particularly with the abbreviation "RI" in them

oai_token-act-pair · gpt-3.5-turbo

references to research institutions or initiatives

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wagon

-0.77

rules

-0.71

forth

-0.70

terson

-0.67

kinson

-0.67

 delay

-0.66

nesium

-0.65

 sands

-0.64

size

-0.64

 Leopard

-0.63

POSITIVE LOGITS

ASON

1.04

KER

1.00

VEN

0.94

BE

0.93

YA

0.93

ARCH

0.92

HCR

0.91

RECT

0.89

JECT

0.88

BLE

0.87

Activations Density 0.008%

terms related to research institutions, particularly with the abbreviation "RI" in them

references to research institutions or initiatives

No Comments

No Known Activations